© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 176068
    Prev
    Next
    INDEX
    Explanations

    hyphen

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cyl
    0.42
     cyl
    0.39
    peza
    0.38
    th
    0.36
    kopp
    0.36
    äure
    0.35
    ct
    0.34
    ↺
    0.34
     themed
    0.34
     probs
    0.34
    POSITIVE LOGITS
    ментів
    0.46
     Mut
    0.45
    Mut
    0.44
    ментов
    0.42
     Muth
    0.42
    ணை
    0.41
    ंतु
    0.39
     Trinidad
    0.39
    ὄ
    0.39
    饪
    0.38
    Activations Density 0.001%

    No Known Activations